© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2325
    Prev
    Next
    INDEX
    Explanations

    technical words and jargon related to technology, biology, and testing

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     using
    -0.85
    using
    -0.77
     utilizing
    -0.66
     USING
    -0.64
    Попис
    -0.63
    USING
    -0.62
    saraba
    -0.62
     leaving
    -0.60
     utilising
    -0.57
     Utilizing
    -0.56
    POSITIVE LOGITS
    instead
    1.07
     instead
    1.04
     interchangeably
    0.95
     вместо
    0.93
    Instead
    0.93
     sparingly
    0.91
     Instead
    0.91
     sebagai
    0.89
    代替
    0.82
    作为
    0.81
    Activations Density 0.806%

    No Known Activations